1PCP-IOSTAT(1)               General Commands Manual              PCP-IOSTAT(1)
2
3
4

NAME

6       pmiostat, pcp-iostat - report block I/O statistics
7

SYNOPSIS

9       pcp  [pcp options]  iostat [-u] [-G method] [-P precision] [-R pattern]
10       [-x [dm][,t][,h][,noidle]]
11

DESCRIPTION

13       pcp-iostat reports I/O  statistics  for  SCSI  (by  default)  or  other
14       devices (if the -x option is specified).
15

OPTIONS

17       When  invoked  via  the  pcp(1)  command,  the -a/--archive, -h/--host,
18       -O/--origin, -s/--samples,  -t/--interval,  -Z/--timezone  and  several
19       other pcp options become indirectly available; refer to PCPIntro(1) for
20       a complete description of these options.
21
22       The additional command line options available for pcp-iostat are:
23
24       -G method, --aggregate=method
25            Specifies that statistics for device names  matching  the  regular
26            expression specified with the -R regex option should be aggregated
27            according to method.  Note this is aggregation based  on  matching
28            device  names  (not  temporal  aggregation).  When -G is used, the
29            device name column is reported as method(regex), e.g.  if  -G  sum
30            -R   'sd(a|b)$'   is   specified,   the   device  column  will  be
31            sum(sd(a|b)$) and summed  statistics  for  sda  and  sdb  will  be
32            reported  in  the remaining columns.  If -G is specified but -R is
33            not specified, then the default regex is  .*,  i.e.  matching  all
34            device  names.   If  method is sum then the statistics are summed.
35            This includes the %util column, which may therefore exceed 100% if
36            more than one device name matches.  If method is avg then the sta‐
37            tistics are summed and then averaged by dividing by the number  of
38            matching  device  names.   If method is min or max, the minimum or
39            maximum statistics for  matching  devices  are  reported,  respec‐
40            tively.
41
42       -P N, --precision=N
43            This indicates the precision (number of decimal places) to report.
44            The default precision N may be set to  something  other  than  the
45            default  (2).   Note  that  the  avgrq-sz  and avgqu-sz fields are
46            always reported with N+1 decimals of precision.  These fields typ‐
47            ically have values less than 1.
48
49       -R pattern, --regex=pattern
50            This  restricts  the  report  to  device  names matching a regular
51            expression pattern.  The given pattern is searched as a perl style
52            regular  expression,  and will match any portion of a device name.
53            e.g. '^sd[a-zA-Z]+' will match all device names starting with 'sd'
54            followed  by  one or more alphabetic characters.  e.g. '^sd(a|b)$'
55            will only match 'sda' and 'sdb'.  e.g. 'sda$' will match 'sda' but
56            not 'sdab'.  See also the -G option for aggregation options.
57
58       -u, --no-interpolation
59            When  replaying  a set of archives, by default values are reported
60            according to  the  requested  sample  interval  (-t  option),  not
61            according  to  the  actual  interval  recorded  in the archive(s).
62            Without this option PCP interpolates the  values  to  be  reported
63            based on the records in the set of archives, which is particularly
64            useful when the -t option is used to replay a set of archives with
65            a longer sampling interval than that with which the archive(s) was
66            originally recorded with.   With  the  -u  option,  uninterpolated
67            reporting  is  enabled  - every value is reported according to the
68            native recording interval in the set of  archives.   When  the  -u
69            option is specified, the -t option makes no sense and is incompat‐
70            ible because the replay interval is always the same as the record‐
71            ing  interval  in  the set of archive.  In addition, -u only makes
72            sense when replaying archives, see the -a option  on  PCPIntro(1),
73            and so if -u is specified then -a must also be specified.
74
75       -x comma-separated-options
76            Specifies a comma-separated list of one or more extended reporting
77            options as follows:
78            dm - report statistics for device-mapper logical  devices  instead
79            of SCSI devices,
80            t  -  prefix every line in the report with a timestamp in ctime(3)
81            format,
82            h - omit the heading, which is otherwise reported  every  24  sam‐
83            ples,
84            noidle - Do not display statistics for idle devices.
85

REPORT

87       The columns in the pcp-iostat report have the following interpretation:
88
89       Timestamp
90              When  the -x t option is specified, this column is the timestamp
91              in ctime(3) format.
92
93       Device Specifies the scsi device name, or if -x dm  is  specified,  the
94              device-mapper  logical  device name.  When -G is specified, this
95              is replaced by the aggregation method and regular  expression  -
96              see the -G and -R options above.
97
98       rrqm/s The  number of read requests expressed as a rate per-second that
99              were merged during the reporting interval by the I/O scheduler.
100
101       wrqm/s The number of write requests expressed as a rate per-second that
102              were merged during the reporting interval by the I/O scheduler.
103
104       r/s    The  number  of  read  requests  completed  by the device (after
105              merges), expressed as a rate per  second  during  the  reporting
106              interval.
107
108       w/s    The  number  of  write  requests  completed by the device (after
109              merges), expressed as a rate per  second  during  the  reporting
110              interval.
111
112       rkB/s  The  average  volume  of  data read from the device expressed as
113              KBytes/second during the reporting interval.
114
115       wkB/s  The average volume of data written to the  device  expressed  as
116              KBytes/second during the reporting interval.
117
118       avgrq-sz
119              The  average  I/O  request size for both reads and writes to the
120              device expressed as Kbytes during the reporting interval.
121
122       avgqu-sz
123              The average queue length of  read  and  write  requests  to  the
124              device during the reporting interval.
125
126       await  The  average  time  in milliseconds that read and write requests
127              were queued (and serviced) to the device  during  the  reporting
128              interval.
129
130       r_await
131              The  average time in milliseconds that read requests were queued
132              (and serviced) to the device during the reporting interval.
133
134       w_await
135              The average time in milliseconds that write requests were queued
136              (and serviced) to the device during the reporting interval.
137
138       %util  The  percentage  of  time during the reporting interval that the
139              device was busy processing requests.  A value of 100%  indicates
140              device saturation.
141

DIAGNOSTICS

143       All  are  generated  on  standard  error  and  are intended to be self-
144       explanatory.
145

PCP ENVIRONMENT

147       Environment variables with the prefix PCP_ are used to parameterize the
148       file  and  directory names used by PCP.  On each installation, the file
149       /etc/pcp.conf contains the  local  values  for  these  variables.   The
150       $PCP_CONF  variable may be used to specify an alternative configuration
151       file, as described in pcp.conf(5).
152
153       For environment variables affecting PCP tools, see pmGetOptions(3).
154

SEE ALSO

156       PCPIntro(1), pcp(1), iostat2pcp(1), pmcd(1),  pmchart(1),  pmlogger(1),
157       pcp.conf(5) and pcp.env(5).
158
159
160
161Performance Co-Pilot                  PCP                        PCP-IOSTAT(1)
Impressum